Training in progress, step 30, checkpoint

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b7d4d4018ff2acd63236135100b3cee3fbea09d6b6a5aad1f5cd50d88571df5b
+oid sha256:bfc605ca010ddf9be2cd0c0b3694da4a0b68e27e749e2b5eae9785f6c803bf20
 size 83115256

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f06fefb228c7af86c90c70c559eb365ce8d42185b182c5ca4ebdd0c11b154fd3
+oid sha256:638818b45897a7a8e7ccc4149583299a7af3fd7e877b09f6ab4100abed72cc59
 size 166439638

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e00a385c6a4231f4efe44b1f8946161a187c9748730e431ce536485fbb3ac425
+oid sha256:c86f6ab54ff37ef2041b4e6013083c27741d0806c10b4a4780a829e4b39ba137
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
+oid sha256:2def2cd24154d8cecbaa07c36ae27e5ebb9b7273a78abfea27aa67c480e4ae2b
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.08676789587852494,
+  "epoch": 0.1301518438177874,
   "eval_steps": 5,
-  "global_step": 20,
+  "global_step": 30,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -89,6 +89,50 @@
       "eval_samples_per_second": 8.686,
       "eval_steps_per_second": 4.343,
       "step": 20
+    },
+    {
+      "epoch": 0.0911062906724512,
+      "grad_norm": 1.8569259643554688,
+      "learning_rate": 8.435655349597689e-05,
+      "loss": 2.2347,
+      "step": 21
+    },
+    {
+      "epoch": 0.10412147505422993,
+      "grad_norm": 1.678497552871704,
+      "learning_rate": 4.12214747707527e-05,
+      "loss": 2.3166,
+      "step": 24
+    },
+    {
+      "epoch": 0.10845986984815618,
+      "eval_loss": 2.2885868549346924,
+      "eval_runtime": 11.2778,
+      "eval_samples_per_second": 8.69,
+      "eval_steps_per_second": 4.345,
+      "step": 25
+    },
+    {
+      "epoch": 0.11713665943600868,
+      "grad_norm": 2.1016781330108643,
+      "learning_rate": 1.0899347581163221e-05,
+      "loss": 2.0839,
+      "step": 27
+    },
+    {
+      "epoch": 0.1301518438177874,
+      "grad_norm": 2.2135860919952393,
+      "learning_rate": 0.0,
+      "loss": 2.411,
+      "step": 30
+    },
+    {
+      "epoch": 0.1301518438177874,
+      "eval_loss": 2.2758893966674805,
+      "eval_runtime": 11.2913,
+      "eval_samples_per_second": 8.679,
+      "eval_steps_per_second": 4.34,
+      "step": 30
     }
   ],
   "logging_steps": 3,
@@ -103,12 +147,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2010596581048320.0,
+  "total_flos": 3015894871572480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null